In some examples, a system includes a memory configured to store a first image and a second image captured by one or more cameras mounted on one or more vehicles and store locations and orientations of the one or more cameras at times when the first and second images were captured. The system also includes processing circuitry configured to identify an existing landmark in the first and second images. The processing circuitry is also configured to determine a latitude, a longitude, and an altitude of the existing landmark based on the locations and orientations of the one or more cameras at the times when the images were captured. The processing circuitry is configured to create a file including the location of the existing landmark and pixel coordinates of the existing landmark in the first and second images.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
3. The system of claim 2, wherein the processing circuitry is further configured to determine the latitude, longitude, and altitude of the first existing landmark based on the locations and the orientations of the one or more cameras at the times when the first and second images were captured in response to determining that the latitude, longitude, and altitude of the first existing landmark are not stored in the pre-existing database.
This system relates to geospatial mapping and landmark localization using camera imagery. The problem addressed is the lack of precise geospatial data for existing landmarks, which is necessary for applications like navigation, augmented reality, and autonomous vehicle positioning. The system determines the latitude, longitude, and altitude of a landmark when this information is missing from a pre-existing database. It uses multiple cameras to capture images of the landmark from different locations and orientations. By analyzing these images, the system calculates the landmark's precise coordinates based on the known positions and orientations of the cameras at the times the images were taken. This approach leverages triangulation or photogrammetric techniques to derive the landmark's 3D position without requiring pre-stored geospatial data. The system ensures accurate geospatial mapping by dynamically determining coordinates when they are unavailable, improving the reliability of location-based services. This method is particularly useful in environments where landmarks are not pre-mapped or where existing databases are incomplete. The system enhances the accuracy of geospatial applications by dynamically filling gaps in landmark data.
15. The method of claim 14, further comprising determining the latitude, longitude, and altitude of the first existing landmark based on the locations and the orientations of the one or more cameras at the times when the first and second images were captured in response to determining that the latitude, longitude, and altitude of the first existing landmark are not stored in the pre-existing database.
This invention relates to a method for determining the geographic coordinates (latitude, longitude, and altitude) of a landmark when such data is not already available in a pre-existing database. The method involves capturing images of the landmark from multiple perspectives using one or more cameras. The cameras' locations and orientations at the times the images were taken are recorded. By analyzing the captured images along with the known camera positions and orientations, the system calculates the landmark's precise geographic coordinates. This approach is particularly useful in scenarios where the landmark's coordinates are unknown or outdated, enabling accurate geospatial mapping and navigation. The method leverages triangulation or other geometric techniques to derive the landmark's position based on the relative positions of the cameras and the landmark's appearance in the images. The determined coordinates are then stored in the database for future reference, improving the accuracy and completeness of geospatial datasets. This solution addresses the challenge of updating or populating geospatial databases with reliable landmark data, which is critical for applications such as autonomous navigation, surveying, and geographic information systems.
16. The method of claim claim 13, further comprising determining the locations and orientations of the one or more cameras at the times when the first and second images were captured based on data from a radar sensor, a lidar sensor, or an ultrasound sensor mounted on the one or more vehicles.
This invention relates to a system for determining the locations and orientations of one or more cameras mounted on vehicles, particularly for use in capturing images of a scene from different perspectives. The problem addressed is the need for accurate positional and orientational data of cameras to enhance the precision of image-based applications, such as 3D reconstruction, autonomous navigation, or environmental mapping. The method involves capturing a first image of a scene from a first camera at a first time and a second image of the same scene from a second camera at a second time. The cameras are mounted on one or more vehicles, which may be moving. To determine the precise locations and orientations of the cameras at the times the images were taken, the system uses data from additional sensors, including radar, lidar, or ultrasound sensors, also mounted on the vehicles. These sensors provide real-time positional and orientational data, which is then correlated with the image capture times to establish the exact positions and angles of the cameras when the images were recorded. This ensures that the images can be accurately aligned and processed for applications requiring high spatial accuracy, such as autonomous driving or augmented reality. The use of multiple sensor types enhances reliability and robustness in varying environmental conditions.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
January 16, 2020
December 20, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.